How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf JIA244601/beijing112telling:Q8_0# Run inference directly in the terminal:
llama-cli -hf JIA244601/beijing112telling:Q8_0Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf JIA244601/beijing112telling:Q8_0# Run inference directly in the terminal:
./llama-cli -hf JIA244601/beijing112telling:Q8_0Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf JIA244601/beijing112telling:Q8_0# Run inference directly in the terminal:
./build/bin/llama-cli -hf JIA244601/beijing112telling:Q8_0Use Docker
docker model run hf.co/JIA244601/beijing112telling:Q8_0Quick Links
Deepseek-r1-Distill-8b-Beijing-History
🤖 模型简介
基于 Google Colab 微调的轻量化模型，专精于北京历史文化领域知识分析（如胡同演变、皇家建筑、民俗文化等），适用于作为大型任务的中间件或领域知识问答工具。
🚀 特性
- 轻量高效：8B 参数量，推理资源需求低
- 领域适配：针对北京历史文本优化，理解地名、事件时间线等细节
- 任务兼容：支持作为 RAG 系统的核心组件或下游任务预处理模块
💻 快速使用
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("JIA244601/beijing112telling")
tokenizer = AutoTokenizer.from_pretrained("JIA244601/beijing112telling")
input_text = "请分析景山在明清两代的功能演变"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0]))
- Downloads last month
- 11
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf JIA244601/beijing112telling:Q8_0# Run inference directly in the terminal: llama-cli -hf JIA244601/beijing112telling:Q8_0